Abstract
Motion capture data could be missing due to imperfections during the acquisition process. Singular value thresholding (SVT) is an effective method to recover missing motion capture data. However, its effectiveness decreases significantly when markers are missing for longer periods of time. To alleviate this problem, we utilize the fact that human bones are rigid to constrain inter-marker distances of specific sets of markers. We extend the SVT method for mocap recovery to include skeleton constraints. On average, our proposed method improves on the SVT method by 40 %, and performs 4 % better than a recent state-of-the-art method at up to 11 times faster computation time.
Similar content being viewed by others
Notes
Mocap data values are scaled down for algorithm stability as recommended, but are not transformed to local coordinates. All parameters are left at default values.
All mocap data values in this paper are expressed in units from the CMU mocap database. To obtain values in millimetres, multiply them by 56.44.
References
Aristidou, A., Cameron, J., Lasenby, J.: Real-time estimation of missing markers in human motion capture. In: The 2nd International Conference on Bioinformatics and Biomedical Engineering, 2008. ICBBE 2008, pp. 1343–1346 (2008)
Aristidou, A., Lasenby, J.: Real-time marker prediction and CoR estimation in optical motion capture. Visual Comput. 29(1), 7–26 (2013)
Baumann, J., Krüger, B., Zinke, A., Weber, A.: Data-driven completion of motion capture data. In: Proceedings of Workshop on Virtual reality interaction and physical simulation (VRIPHYS) (2011)
Cai, J.F., Candès, E.J., Shen, Z.: A singular value thresholding algorithm for matrix completion. SIAM J. Optim. 20(4), 1956–1982 (2010)
Candès, E., Recht, B.: Exact matrix completion via convex optimization. Found. Comput. Math. 9(6), 717–772 (2009)
Chai, J., Hodgins, J.K.: Performance animation from low-dimensional control signals. ACM Trans. Graph. 24(3), 686–696 (2005)
CMU: CMU graphics lab motion capture database. http://mocap.cs.cmu.edu/ (2012)
Dorfmüller-Ulhaas, K.: Robust optical user motion tracking using a kalman filter. In: 10th ACM Symposium on Virtual Reality Software and Technology (2003)
Grochow, K., Martin, S.L., Hertzmann, A., Popović, Z.: Style-based inverse kinematics. ACM SIGGRAPH 2004 Papers. SIGGRAPH ’04, pp. 522–531. ACM, New York, NY, USA (2004)
Herda, L., Fua, P., Plankers, R., Boulic, R., Thalmann, D.: Skeleton-based motion capture for robust reconstruction of human motion. In: Computer Animation 2000. Proceedings, pp. 77–83 (2000)
Herda, L., Fua, P., Plänkers, R., Boulic, R., Thalmann, D.: Using skeleton-based tracking to increase the reliability of optical motion capture. Hum. Mov. Sci. 20(3), 313–341 (2001)
Hornung, A., Sar-Dessai, S., Kobbelt, L.: Self-calibrating optical motion tracking for articulated bodies. In: IEEE Virtual Reality, 2005. Proceedings. VR 2005, pp. 75–82 (2005)
Hou, J., Chau, L.P., He, Y., Chen, J., Magnenat-Thalmann, N.: Human motion capture data recovery via trajectory-based sparse representation. In: Proc. IEEE International Conference on Image processing (ICIP) (2013)
Hou, J., Bian, Z.-P., Chau, L.P., He, Y., Magnenat-Thalmann, N.: Restoring Corrupted Motion Capture Data via Jointly Low-Rank Matrix Recovery. In: Proc. IEEE International Conference on Multimedia & Expo (ICME) (2014)
Krüger, B., Tautges, J., Weber, A., Zinke, A.: Fast local and global similarity searches in large motion capture databases. In: Proceedings of the 2010 ACM SIGGRAPH/Eurographics Symposium on Computer animation. SCA ’10, pp. 1–10. Eurographics Association, Aire-la-Ville, Switzerland, Switzerland (2010)
Lai, R., Yuen, P., Lee, K.: Motion capture data completion and denoising by singular value thresholding. In: Eurographics 2011-Short Papers, pp. 45–48 (2011)
Lawrence, N.: Gaussian process latent variable models for visualisation of high dimensional data. In: S. Thrun, L. Saul, B. schölkopf (eds.) Advances in Neural Information Processing Systems 16, pp. 329–336. MIT Press, Cambridge, MA (2004)
Li, L., McCann, J., Pollard, N., Faloutsos, C.: BoLeRO: a principled technique for including bone length constraints in motion capture occlusion filling. In: Proceedings of the 2010 ACM SIGGRAPH/Eurographics Symposium on Computer animation. SCA ’10, pp. 179–188. Eurographics Association, Aire-la-Ville, Switzerland, Switzerland (2010)
Li, L., McCann, J., Pollard, N.S., Faloutsos, C.: DynaMMo: mining and summarization of coevolving sequences with missing values. In: Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining, pp. 507–516. ACM, New York, NY, USA (2009)
Liu, G., McMillan, L.: Estimation of missing markers in human motion capture. Visual Comput. 22(9–11), 721–728 (2006)
Lou, H., Chai, J.: Example-based human motion denoising. IEEE Trans. Vis. Comput. Graph. 16(5), 870–879 (2010)
Papadimitriou, S., Brockwell, A., Faloutsos, C.: Adaptive, hands-off stream mining. In: Proceedings of the 29th international conference on Very large data bases - Volume 29, VLDB ’03, pp. 560–571. VLDB Endowment (2003)
Piazza, T., Lundström, J., Kunz, A., Fjeld, M.: Predicting missing markers in real-time optical motion capture. In: Proceedings of the 2009 international conference on Modelling the physiological human, p. 125–136. Springer (2009)
Tan, C.H., Hou, J., Chau, L.P.: Human motion capture data recovery using trajectory-based matrix completion. Electron. Lett. 49(12), 752–754 (2013)
Taylor, G.W., Hinton, G.E., Roweis, S.: Modeling human motion using binary latent variables. In: Advances in Neural Information Processing Systems, pp. 1345–1352. MIT Press, Cambridge, MA (2007)
Wang, J., Fleet, D., Hertzmann, A.: Gaussian process dynamical models for human motion. IEEE Trans. Pattern Anal. Mach. Intel. 30(2), 283–298 (2008)
Wiley, D., Hahn, J.: Interpolation synthesis for articulated figure motion. In: Virtual Reality Annual International Symposium, 1997, IEEE 1997, pp. 156–160 (1997)
**ao, J., Feng, Y., Hu, W.: Predicting missing markers in human motion capture using l1-sparse representation. Comput. Anim. Virtual Worlds 22(2–3), 221–228 (2011)
Yi, B.K., Sidiropoulos, N., Johnson, T., Jagadish, H., Faloutsos, C., Biliris, A.: Online data mining for co-evolving time sequences. In: 16th International Conference on Data engineering, 2000. Proceedings, pp. 13–22 (2000)
Yi, P., Zhang, Q., Wei, X.: Laplacian coordinates-based motion transition for data-driven motion synthesis. IET Image Process. 6(9), 1331–1337 (2012)
Zhou, F., De la Torre, F., Hodgins, J.: Hierarchical aligned cluster analysis for temporal clustering of human motion. Pattern Anal. Mach. Intel. IEEE Trans. 35(3), 582–596 (2013)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Tan, CH., Hou, J. & Chau, LP. Motion capture data recovery using skeleton constrained singular value thresholding. Vis Comput 31, 1521–1532 (2015). https://doi.org/10.1007/s00371-014-1031-5
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00371-014-1031-5